Deeply-Learned Part-Aligned Representations for Person Re-identification

Li-ming, Zhao; Li, Xi; Zhuang, Yueting; Wang, Jingdong

doi:10.1109/iccv.2017.349

Cited by 770 publications

(492 citation statements)

References 57 publications

Supporting

Mentioning

487

Contrasting

Order By: Relevance

“…To alleviate the adverse influence from the backgrounds, numerous methods [1], [2], [3], [4], [5], [6], [7], [8], [9] have been proposed. In [1], [2], [3], human landmark detectors are used to extract human keypoints and generate human part bounding boxes.…”

Section: Introductionmentioning

confidence: 99%

End-to-End Comparative Attention Networks for Person Re-Identification

Líu¹,

Feng²,

Qi³

et al. 2017

IEEE Trans. on Image Process.

562

317

View full text Add to dashboard Cite

Abstract-Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies in the lack of spatial and temporal cues, which makes it difficult to deal with large variations of lighting conditions, viewing angles, body poses and occlusions. Recently, several deep learning based person re-identification approaches have been proposed and achieved remarkable performance. However, most of those approaches extract discriminative features from the whole frame at one glimpse without differentiating various parts of the persons to identify. It is essentially important to examine multiple highly discriminative local regions of the person images in details through multiple glimpses for dealing with the large appearance variance.In this paper, we propose a new soft attention based model, i.e., the end-to-end Comparative Attention Network (CAN), specifically tailored for the task of person re-identification. The end-to-end CAN learns to selectively focus on parts of pairs of person images after taking a few glimpses of them and adaptively comparing their appearance. The CAN model is able to learn which parts of images are relevant for discerning persons and automatically integrates information from different parts to determine whether a pair of images belongs to the same person. In other words, our proposed CAN model simulates the human perception process to verify whether two images are from the same person. Extensive experiments on four benchmark person re-identification datasets, including CUHK01, CHUHK03, Market-1501 and VIPeR, clearly demonstrate that our proposed end-to-end CAN for person re-identification outperforms well established baselines significantly and offer new state-of-the-art performance.

show abstract

Section: Introductionmentioning

confidence: 99%

End-to-End Comparative Attention Networks for Person Re-Identification

Líu¹,

Feng²,

Qi³

et al. 2017

IEEE Trans. on Image Process.

562

317

View full text Add to dashboard Cite

show abstract

“…Only K-LFDA when trained with mom LE [24] feature attains comparable performance than DMN. However, motivated to resolve the challenges for reidentification in real world (i.e., multimodal image space, and diverse impostors) IRM3 + CVI ( = 15) has much better results than MCP-CNN [39], E2E-CAN [31], Quadruplet-Net [33], and JLML [34], while our IRM3 + CVI ( = 15) has 1.49% higher rank@1 than DLPA [32]. DLPA extracts deep features by semantically aligning body parts, as well as rectifying pose variations.…”

Section: Results On Cuhk01mentioning

confidence: 99%

“…These high results demonstrate the fact that CUHK03 is the largest dataset among all and, thus, can help in learning a more discriminative DMN. Even though both JLML [34] and DLPA [32] learn deep body features with global and local body parts alignment, as well as, pose alignment, however, our IMR3 approach benefitted with transform specific metrics empowered with impostors rejection still maintained to attain better results. Our IRM3 Advances in Multimedia 9 considers optimizing all the rank orders simultaneously and, thus, have large gain at rank@5 and rank@10 in Labelled setting.…”

Section: Results On Cuhk03mentioning

confidence: 99%

Impostor Resilient Multimodal Metric Learning for Person Reidentification

Syed

Han

et al. 2018

Advances in Multimedia

View full text Add to dashboard Cite

In person reidentification distance metric learning suffers a great challenge from impostor persons. Mostly, distance metrics are learned by maximizing the similarity between positive pair against impostors that lie on different transform modals. In addition, these impostors are obtained from Gallery view for query sample only, while the Gallery sample is totally ignored. In real world, a given pair of query and Gallery experience different changes in pose, viewpoint, and lighting. Thus, impostors only from Gallery view can not optimally maximize their similarity. Therefore, to resolve these issues we have proposed an impostor resilient multimodal metric (IRM3). IRM3 is learned for each modal transform in the image space and uses impostors from both Probe and Gallery views to effectively restrict large number of impostors. Learned IRM3 is then evaluated on three benchmark datasets, VIPeR, CUHK01, and CUHK03, and shows significant improvement in performance compared to many previous approaches.

show abstract

“…Yao et al [26] proposed the Part Loss Networks (PL-Net) to automatically detect human parts and cross train them with the main identity task. Zhao et al [27] follows the concept of attention model and uses a part map detector to extract multiple body regions in order to compute their corresponding representations. The model is learned through triplet loss function.…”

Section: Aam Heatmapmentioning

confidence: 99%

AANet: Attribute Attention Network for Person Re-Identifications

Tay

Roy

Yap

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

342

155

View full text Add to dashboard Cite

This paper proposes Attribute Attention Network (AANet), a new architecture that integrates person attributes and attribute attention maps into a classification framework to solve the person re-identification (re-ID) problem. Many person re-ID models typically employ semantic cues such as body parts or human pose to improve the re-ID performance. Attribute information, however, is often not utilized. The proposed AANet leverages on a baseline model that uses body parts and integrates the key attribute information in an unified learning framework. The AANet consists of a global person ID task, a part detection task and a crucial attribute detection task. By estimating the class responses of individual attributes and combining them to form the attribute attention map (AAM), a very strong discriminatory representation is constructed. The proposed AANet outperforms the best state-of-the-art method [22] using ResNet-50 by 3.36% in mAP and 3.12% in Rank-1 accuracy on DukeMTMC-reID dataset. On Market1501 dataset, AANet achieves 92.38% mAP and 95.10% Rank-1 accuracy with re-ranking, outperforming [13], another state of the art method using ResNet-152, by 1.42% in mAP and 0.47% in Rank-1 accuracy. In addition, AANet can perform person attribute prediction (e.g., gender, hair length, clothing length etc.), and localize the attributes in the query image.

show abstract

Deeply-Learned Part-Aligned Representations for Person Re-identification

Cited by 770 publications

References 57 publications

End-to-End Comparative Attention Networks for Person Re-Identification

End-to-End Comparative Attention Networks for Person Re-Identification

Impostor Resilient Multimodal Metric Learning for Person Reidentification

AANet: Attribute Attention Network for Person Re-Identifications

Contact Info

Product

Resources

About